Mikaela Angelina Uy
Papers
2
Total Citations
6
H-Index
2
About
Mikaela Angelina Uy is a rising star in computer vision and 3D geometric deep learning, whose work bridges the gap between visual perception and structured 3D representations. Her primary research focuses on reverse engineering 3D computer-aided design (CAD) models from images—a task critical for interactive editing, manufacturing, architecture, and robotics. In her highly cited work, "Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization" (2024–2025), Uy tackles the fundamental challenge of converting unstructured image data into precise, parametric CAD models. By leveraging vision-language models (VLMs) for conditional factorization, her method disentangles complex shape representations into editable, manufacturable components. This contribution addresses a long-standing representational disparity between raw visual inputs and structured CAD outputs, enabling downstream applications that require both geometric accuracy and semantic understanding. With early citations already accumulating, Uy’s work is rapidly gaining recognition for its practical impact in robotics and digital fabrication. Her research exemplifies how combining modern vision-language techniques with classical geometric reasoning can unlock new capabilities in 3D content creation and reverse engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2